Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

Abstract

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the source domain. Pre-trained deep neural networks are used to generate deep features having high transferability across related domains. We perform an extensive experimental analysis of the proposed method over a wide set of publicly available pre-trained deep neural networks. Results of our experiments on domain adaptation tasks for image classification show that class prediction uncertainty alignment with features extracted from pre-trained deep neural networks provides an efficient, robust and effective method for domain adaptation.

arXiv commentTo appear in ICPRAM 2019

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• How transferable are features in deep neural networks?
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Domain Separation Networks
• Unsupervised Cross-Domain Image Generation
• Xception: Deep Learning with Depthwise Separable Convolutions
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Domain-Adversarial Neural Networks
• Deep Transfer Network: Unsupervised Domain Adaptation
• Deep Transfer Learning with Joint Adaptation Networks
• A Testbed for Cross-Dataset Analysis

Cited by in corpus (8)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Domain-Specific Batch Normalization for Unsupervised Domain Adaptation
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent
• Hidden Covariate Shift: A Minimal Assumption For Domain Adaptation
• Adapting Vehicle Detector to Target Domain by Adversarial Prediction Alignment
• LRS-DAG: Low Resource Supervised Domain Adaptation with Generalization Across Domains
• Brain Tumor Segmentation on MRI with Missing Modalities